Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a29547928899e9abc6d4a17dbc1365266ff59c6aaeb4a7d77a24c891710f93
+oid sha256:48b4b5d25336857b942e4107105c947901c157cd0ce2b2a58c29401af1aaf7df
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d32e02f8c6947353112495df81a173176f70714456bb66738381753ff0ebc9
+oid sha256:930f9c66a98e80119beff7dce8df3d85221799820394feb7bebaacd8fb4bf201
 size 1324282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1aadfafad9038d7bc765693aa4a3cc4ff625365f83d6f40db54ca1c6dc6ef74
+oid sha256:e04552e5b6090b36f415797cc1109f0fb451463ea25faacb629fa74f503afc2b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
+oid sha256:71a96715f430c2eb0d6104363f54769b2c1bdb005671dc81f0d67833a84ba743
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.682699203491211,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.08982932428386066,
+  "best_metric": 11.682429313659668,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.09981036031540073,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 66.862,
       "eval_steps_per_second": 16.731,
       "step": 450
+    },
+    {
+      "epoch": 0.09182553149016869,
+      "grad_norm": 0.09359036386013031,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 11.7352,
+      "step": 460
+    },
+    {
+      "epoch": 0.0938217386964767,
+      "grad_norm": 0.08482491970062256,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 11.7345,
+      "step": 470
+    },
+    {
+      "epoch": 0.09581794590278471,
+      "grad_norm": 0.08152854442596436,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 11.7306,
+      "step": 480
+    },
+    {
+      "epoch": 0.09781415310909272,
+      "grad_norm": 0.08653771132230759,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 11.7125,
+      "step": 490
+    },
+    {
+      "epoch": 0.09981036031540073,
+      "grad_norm": 0.460737407207489,
+      "learning_rate": 0.0,
+      "loss": 11.5164,
+      "step": 500
+    },
+    {
+      "epoch": 0.09981036031540073,
+      "eval_loss": 11.682429313659668,
+      "eval_runtime": 31.3753,
+      "eval_samples_per_second": 67.25,
+      "eval_steps_per_second": 16.829,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 63221776515072.0,
+  "total_flos": 70331052589056.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null